Quentin Gallouédec

> > reporting result for both settings separated ([MuZero](https://arxiv.org/pdf/2104.06294v1.pdf)) . > > Could you point me to the page or table number for both settings? Table 12 and section 7....

Hi @jenschwich, check out https://github.com/Stable-Baselines-Team/rl-colab-notebooks/blob/sb3/README.md

Some progress! The code in https://github.com/DLR-RM/stable-baselines3/pull/951#issuecomment-1214373828 now ('2.0.0.dev20230214') outputs ```log /Users/quentingallouedec/stable-baselines3/env/lib/python3.10/site-packages/torch/distributions/categorical.py:118: UserWarning: 1MPS: no support for int64 min/max ops, casting it to int32 (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/native/mps/operations/ReduceOps.mm:1260.) samples_2d = torch.multinomial(probs_2d,...

The number of errors decreases. Here's one a them: ``` TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead....

@tty666 thank you for the proposal. Feel free to test and provide your feedback if any. As far as I remember, there are still some issues related to dtype (float64...

Hi @theSquaredError, I would be happy to help you with your first open-source contribution. I advise you to follow the step described in https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md. Don't hesitate to contact me if...

This one is just about updating the documentation, from "log every n timeteps" to "log every n episodes".

This is because you are trying to push to the master branch, which is protected. Here is a step-by-step process you can follow https://github.com/firstcontributions/first-contributions.

Which versions of gym/gymnasium/sb3 are you using?

I'm pretty sure you use gymnasium